# Active Learning in Robotics: A Review of Control Principles

arXiv: https://arxiv.org/abs/2106.13697 · HTML: https://mlsanity.com/paper/2106.13697/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2021.

## Built on by (most cited first, 26 of 26)

- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Autoregressive Action Sequence Learning for Robotic Manipulation](https://mlsanity.com/paper/2410.03132/) (2024)
- [Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science](https://mlsanity.com/paper/2603.15381/) (2026)
- [Maximum diffusion reinforcement learning](https://mlsanity.com/paper/2309.15293/) (2023)
- [Brain-inspired Artificial Intelligence: A Comprehensive Review](https://mlsanity.com/paper/2408.14811/) (2024)
- [Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI](https://mlsanity.com/paper/2410.23630/) (2024)
- [Sample-efficient and Scalable Exploration in Continuous-Time RL](https://mlsanity.com/paper/2510.24482/) (2025)
- [Information theory and discriminative sampling for model discovery](https://mlsanity.com/paper/2512.16000/) (2025)
- [Weighted Ensembles for Active Learning with Adaptivity](https://mlsanity.com/paper/2206.05009/) (2022)
- [The Psychophysics of Human Three-Dimensional Active Visuospatial Problem-Solving](https://mlsanity.com/paper/2306.11756/) (2023)
- [Apple: Toward General Active Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.06182/) (2025)
- [Enhancing Robot Navigation Policies with Task-Specific Uncertainty Managements](https://mlsanity.com/paper/2505.13837/) (2025)
- [Sample Efficient Robot Learning in Supervised Effect Prediction Tasks](https://mlsanity.com/paper/2412.02331/) (2024)
- [SODAs: Sparse Optimization for the Discovery of Differential and Algebraic Equations](https://mlsanity.com/paper/2503.05993/) (2025)
- [Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review](https://mlsanity.com/paper/2505.07911/) (2025)
- [UAV-aided RF Mapping for Sensing and Connectivity in Wireless Networks](https://mlsanity.com/paper/2205.03335/) (2022)
- [Automatic Truss Design with Reinforcement Learning](https://mlsanity.com/paper/2306.15182/) (2023)
- [Value of Assistance for Grasping](https://mlsanity.com/paper/2310.14402/) (2023)
- [Optimal Potential Shaping on SE(3) via Neural ODEs on Lie Groups](https://mlsanity.com/paper/2401.15107/) (2024)
- [Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation](https://mlsanity.com/paper/2404.01867/) (2024)
- [A Computational Model of Inclusive Pedagogy: From Understanding to Application](https://mlsanity.com/paper/2505.02853/) (2025)
- [ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation](https://mlsanity.com/paper/2506.04646/) (2025)
- [Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems](https://mlsanity.com/paper/2506.22186/) (2025)
- [Generalized Information Gathering Under Dynamics Uncertainty](https://mlsanity.com/paper/2601.21988/) (2026)
- [SocioGesture: Real-Time and Adaptive Social Gesture Perception for Human-Robot Interaction](https://mlsanity.com/paper/2609.04545/) (2026)
- [Information-theoretic receding-horizon active learning of nonlinear dynamical systems](https://mlsanity.com/paper/2609.36712/) (2026)

## Abstract (arXiv)

Active learning is a decision-making process. In both abstract and physical settings, active learning demands both analysis and action. This is a review of active learning in robotics, focusing on methods amenable to the demands of embodied learning systems. Robots must be able to learn efficiently and flexibly through continuous online deployment. This poses a distinct set of control-oriented challenges -- one must choose suitable measures as objectives, synthesize real-time control, and produce analyses that guarantee performance and safety with limited knowledge of the environment or robot itself. In this work, we survey the fundamental components of robotic active learning systems. We discuss classes of learning tasks that robots typically encounter, measures with which they gauge the information content of observations, and algorithms for generating action plans. Moreover, we provide a variety of examples -- from environmental mapping to nonparametric shape estimation -- that highlight the qualitative differences between learning tasks, information measures, and control techniques. We conclude with a discussion of control-oriented open challenges, including safety-constrained learning and distributed learning.